BANDIT SAMPLING FOR FASTER NEURAL NETWORK TRAINING WITH SGD.

Vignesh Ganapathiraman Francisco Javier Calderon Anila Joshi

Published in: Tiny Papers @ ICLR (2023)

Keyphrases

neural network training
random sampling
training algorithm
neural network
optimization method
multi armed bandit
active learning
genetic algorithm
stochastic gradient descent
expert systems
feature space
learning process
probabilistic model
state space